Python70-tensorflow训练模型以及利用保存的模型做预测.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "原文：https://blog.csdn.net/randompeople/article/details/75561364"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 实例\n",
    "利用mnist语料集做的例子来熟悉保存训练模型的参数用来做预测，首先会出贴出保存模型的案例代码，然后会贴出预测的代码。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Extracting ./MNIST_data\\train-images-idx3-ubyte.gz\n",
      "Extracting ./MNIST_data\\train-labels-idx1-ubyte.gz\n",
      "Extracting ./MNIST_data\\t10k-images-idx3-ubyte.gz\n",
      "Extracting ./MNIST_data\\t10k-labels-idx1-ubyte.gz\n"
     ]
    }
   ],
   "source": [
    "# encoding=utf-8\n",
    "\n",
    "from __future__ import print_function\n",
    "\n",
    "import tensorflow as tf\n",
    "\n",
    "# Import MNIST data\n",
    "from tensorflow.examples.tutorials.mnist import input_data\n",
    "mnist = input_data.read_data_sets(\"./MNIST_data\", one_hot=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 设置参数\n",
    "learning_rate = 0.001\n",
    "training_iters = 128*10*300 \n",
    "batch_size = 128\n",
    "display_step = 10"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 神经网络参数\n",
    "n_input = 784 # MNIST data input (img shape: 28*28)\n",
    "n_classes = 10 # MNIST total classes (0-9 digits)\n",
    "dropout = 0.75 # Dropout, probability to keep units"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [],
   "source": [
    "# tf Graph input\n",
    "x = tf.placeholder(tf.float32, [None, n_input])\n",
    "y = tf.placeholder(tf.float32, [None, n_classes])\n",
    "keep_prob = tf.placeholder(tf.float32) #dropout (keep probability)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 模型"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create some wrappers for simplicity\n",
    "def conv2d(x, W, b, strides=1):\n",
    "    # Conv2D wrapper, with bias and relu activation\n",
    "    x = tf.nn.conv2d(x, W, strides=[1, strides, strides, 1], padding='SAME')\n",
    "    x = tf.nn.bias_add(x, b)\n",
    "    return tf.nn.relu(x)\n",
    "\n",
    "def maxpool2d(x, k=2):\n",
    "    # MaxPool2D wrapper\n",
    "    return tf.nn.max_pool(x, ksize=[1, k, k, 1], strides=[1, k, k, 1],\n",
    "                          padding='SAME')\n",
    "\n",
    "# Create model\n",
    "def conv_net(x, weights, biases, dropout):\n",
    "    # Reshape input picture\n",
    "    x = tf.reshape(x, shape=[-1, 28, 28, 1])\n",
    "\n",
    "    # Convolution Layer\n",
    "    conv1 = conv2d(x, weights['wc1'], biases['bc1'])\n",
    "    # Max Pooling (down-sampling)\n",
    "    conv1 = maxpool2d(conv1, k=2)\n",
    "\n",
    "    # Convolution Layer\n",
    "    conv2 = conv2d(conv1, weights['wc2'], biases['bc2'])\n",
    "    # Max Pooling (down-sampling)\n",
    "    conv2 = maxpool2d(conv2, k=2)\n",
    "\n",
    "    # Fully connected layer\n",
    "    # Reshape conv2 output to fit fully connected layer input\n",
    "    fc1 = tf.reshape(conv2, [-1, weights['wd1'].get_shape().as_list()[0]])\n",
    "    fc1 = tf.add(tf.matmul(fc1, weights['wd1']), biases['bd1'])\n",
    "    fc1 = tf.nn.relu(fc1)\n",
    "    # Apply Dropout\n",
    "    fc1 = tf.nn.dropout(fc1, dropout)\n",
    "\n",
    "    # Output, class prediction\n",
    "    out = tf.add(tf.matmul(fc1, weights['out']), biases['out'])\n",
    "    return out"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 训练模型"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [],
   "source": [
    "weights = {\n",
    "    # 5x5 conv, 1 input, 32 outputs\n",
    "    'wc1': tf.Variable(tf.random_normal([5, 5, 1, 32])),\n",
    "    # 5x5 conv, 32 inputs, 64 outputs\n",
    "    'wc2': tf.Variable(tf.random_normal([5, 5, 32, 64])),\n",
    "    # fully connected, 7*7*64 inputs, 1024 outputs\n",
    "    'wd1': tf.Variable(tf.random_normal([7*7*64, 1024])),\n",
    "    # 1024 inputs, 10 outputs (class prediction)\n",
    "    'out': tf.Variable(tf.random_normal([1024, n_classes]))\n",
    "}\n",
    "biases = {\n",
    "    'bc1': tf.Variable(tf.random_normal([32])),\n",
    "    'bc2': tf.Variable(tf.random_normal([64])),\n",
    "    'bd1': tf.Variable(tf.random_normal([1024])),\n",
    "    'out': tf.Variable(tf.random_normal([n_classes]))\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Optimization Finished!\n",
      "save model\n",
      "save model:./Test_MNIST_model.ckpt Finished\n",
      "Testing Accuracy: 0.98046875\n"
     ]
    }
   ],
   "source": [
    "# Construct model\n",
    "pred = conv_net(x,weights, biases, keep_prob)\n",
    "\n",
    "# Define loss and optimizer\n",
    "cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))\n",
    "optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)\n",
    "\n",
    "# Evaluate model\n",
    "correct_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))\n",
    "accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))\n",
    "\n",
    "# Initializing the variables\n",
    "init = tf.global_variables_initializer()\n",
    "\n",
    "saver = tf.train.Saver()  ##保存的API\n",
    "# Launch the graph\n",
    "with tf.Session() as sess:\n",
    "    sess.run(init)\n",
    "    step = 1\n",
    "    # Keep training until reach max iterations\n",
    "    while step * batch_size < training_iters:\n",
    "        batch_x, batch_y = mnist.train.next_batch(batch_size)\n",
    "        # Run optimization op (backprop)\n",
    "        sess.run(optimizer, feed_dict={x: batch_x, y: batch_y,\n",
    "                                       keep_prob: dropout})\n",
    "        if step % display_step == 0:\n",
    "            # Calculate batch loss and accuracy\n",
    "            loss, acc = sess.run([cost, accuracy], feed_dict={x: batch_x,\n",
    "                                                              y: batch_y,\n",
    "                                                              keep_prob: 1.})\n",
    "#             print(\"Iter \" + str(step*batch_size) + \", Minibatch Loss= \" + \\\n",
    "#                   \"{:.6f}\".format(loss) + \", Training Accuracy= \" + \\\n",
    "#                   \"{:.5f}\".format(acc))\n",
    "        step += 1\n",
    "    print(\"Optimization Finished!\")\n",
    "    print(\"save model\")\n",
    "    save_path = saver.save(sess,\"./Test_MNIST_model.ckpt\")  #保存模型\n",
    "    print(\"save model:{0} Finished\".format(save_path))\n",
    "\n",
    "    # Calculate accuracy for 256 mnist test images\n",
    "    print(\"Testing Accuracy:\", \\\n",
    "        sess.run(accuracy, feed_dict={x: mnist.test.images[:256],\n",
    "                                      y: mnist.test.labels[:256],\n",
    "                                      keep_prob: 1.}))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 读取模型来预测测试集的分类结果"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Extracting ./MNIST_data\\train-images-idx3-ubyte.gz\n",
      "Extracting ./MNIST_data\\train-labels-idx1-ubyte.gz\n",
      "Extracting ./MNIST_data\\t10k-images-idx3-ubyte.gz\n",
      "Extracting ./MNIST_data\\t10k-labels-idx1-ubyte.gz\n",
      "INFO:tensorflow:Restoring parameters from ./result/Test_MNIST_model.ckpt\n"
     ]
    },
    {
     "ename": "NotFoundError",
     "evalue": "Key Variable_100 not found in checkpoint\n\t [[Node: save_9/RestoreV2 = RestoreV2[dtypes=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, ..., DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT], _device=\"/job:localhost/replica:0/task:0/device:CPU:0\"](_arg_save_9/Const_0_0, save_9/RestoreV2/tensor_names, save_9/RestoreV2/shape_and_slices)]]\n\nCaused by op 'save_9/RestoreV2', defined at:\n  File \"E:\\ProgramData\\Anaconda3\\lib\\runpy.py\", line 193, in _run_module_as_main\n    \"__main__\", mod_spec)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\runpy.py\", line 85, in _run_code\n    exec(code, run_globals)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\ipykernel_launcher.py\", line 16, in <module>\n    app.launch_new_instance()\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\traitlets\\config\\application.py\", line 658, in launch_instance\n    app.start()\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\ipykernel\\kernelapp.py\", line 486, in start\n    self.io_loop.start()\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\tornado\\platform\\asyncio.py\", line 127, in start\n    self.asyncio_loop.run_forever()\n  File \"E:\\ProgramData\\Anaconda3\\lib\\asyncio\\base_events.py\", line 422, in run_forever\n    self._run_once()\n  File \"E:\\ProgramData\\Anaconda3\\lib\\asyncio\\base_events.py\", line 1432, in _run_once\n    handle._run()\n  File \"E:\\ProgramData\\Anaconda3\\lib\\asyncio\\events.py\", line 145, in _run\n    self._callback(*self._args)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\tornado\\ioloop.py\", line 759, in _run_callback\n    ret = callback()\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\tornado\\stack_context.py\", line 276, in null_wrapper\n    return fn(*args, **kwargs)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\zmq\\eventloop\\zmqstream.py\", line 536, in <lambda>\n    self.io_loop.add_callback(lambda : self._handle_events(self.socket, 0))\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\zmq\\eventloop\\zmqstream.py\", line 450, in _handle_events\n    self._handle_recv()\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\zmq\\eventloop\\zmqstream.py\", line 480, in _handle_recv\n    self._run_callback(callback, msg)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\zmq\\eventloop\\zmqstream.py\", line 432, in _run_callback\n    callback(*args, **kwargs)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\tornado\\stack_context.py\", line 276, in null_wrapper\n    return fn(*args, **kwargs)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\ipykernel\\kernelbase.py\", line 283, in dispatcher\n    return self.dispatch_shell(stream, msg)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\ipykernel\\kernelbase.py\", line 233, in dispatch_shell\n    handler(stream, idents, msg)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\ipykernel\\kernelbase.py\", line 399, in execute_request\n    user_expressions, allow_stdin)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\ipykernel\\ipkernel.py\", line 208, in do_execute\n    res = shell.run_cell(code, store_history=store_history, silent=silent)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\ipykernel\\zmqshell.py\", line 537, in run_cell\n    return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\IPython\\core\\interactiveshell.py\", line 2662, in run_cell\n    raw_cell, store_history, silent, shell_futures)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\IPython\\core\\interactiveshell.py\", line 2785, in _run_cell\n    interactivity=interactivity, compiler=compiler, result=result)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\IPython\\core\\interactiveshell.py\", line 2903, in run_ast_nodes\n    if self.run_code(code, result):\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\IPython\\core\\interactiveshell.py\", line 2963, in run_code\n    exec(code_obj, self.user_global_ns, self.user_ns)\n  File \"<ipython-input-52-1c6db3348267>\", line 92, in <module>\n    saver = tf.train.Saver()  ##保存的API\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\training\\saver.py\", line 1338, in __init__\n    self.build()\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\training\\saver.py\", line 1347, in build\n    self._build(self._filename, build_save=True, build_restore=True)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\training\\saver.py\", line 1384, in _build\n    build_save=build_save, build_restore=build_restore)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\training\\saver.py\", line 835, in _build_internal\n    restore_sequentially, reshape)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\training\\saver.py\", line 472, in _AddRestoreOps\n    restore_sequentially)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\training\\saver.py\", line 886, in bulk_restore\n    return io_ops.restore_v2(filename_tensor, names, slices, dtypes)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\ops\\gen_io_ops.py\", line 1546, in restore_v2\n    shape_and_slices=shape_and_slices, dtypes=dtypes, name=name)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\framework\\op_def_library.py\", line 787, in _apply_op_helper\n    op_def=op_def)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\framework\\ops.py\", line 3392, in create_op\n    op_def=op_def)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\framework\\ops.py\", line 1718, in __init__\n    self._traceback = self._graph._extract_stack()  # pylint: disable=protected-access\n\nNotFoundError (see above for traceback): Key Variable_100 not found in checkpoint\n\t [[Node: save_9/RestoreV2 = RestoreV2[dtypes=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, ..., DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT], _device=\"/job:localhost/replica:0/task:0/device:CPU:0\"](_arg_save_9/Const_0_0, save_9/RestoreV2/tensor_names, save_9/RestoreV2/shape_and_slices)]]\n",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mNotFoundError\u001b[0m                             Traceback (most recent call last)",
      "\u001b[1;32mE:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\client\\session.py\u001b[0m in \u001b[0;36m_do_call\u001b[1;34m(self, fn, *args)\u001b[0m\n\u001b[0;32m   1321\u001b[0m     \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1322\u001b[1;33m       \u001b[1;32mreturn\u001b[0m \u001b[0mfn\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1323\u001b[0m     \u001b[1;32mexcept\u001b[0m \u001b[0merrors\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mOpError\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mE:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\client\\session.py\u001b[0m in \u001b[0;36m_run_fn\u001b[1;34m(feed_dict, fetch_list, target_list, options, run_metadata)\u001b[0m\n\u001b[0;32m   1306\u001b[0m       return self._call_tf_sessionrun(\n\u001b[1;32m-> 1307\u001b[1;33m           options, feed_dict, fetch_list, target_list, run_metadata)\n\u001b[0m\u001b[0;32m   1308\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mE:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\client\\session.py\u001b[0m in \u001b[0;36m_call_tf_sessionrun\u001b[1;34m(self, options, feed_dict, fetch_list, target_list, run_metadata)\u001b[0m\n\u001b[0;32m   1408\u001b[0m           \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_session\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0moptions\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfeed_dict\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfetch_list\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtarget_list\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1409\u001b[1;33m           run_metadata)\n\u001b[0m\u001b[0;32m   1410\u001b[0m     \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mNotFoundError\u001b[0m: Key Variable_100 not found in checkpoint\n\t [[Node: save_9/RestoreV2 = RestoreV2[dtypes=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, ..., DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT], _device=\"/job:localhost/replica:0/task:0/device:CPU:0\"](_arg_save_9/Const_0_0, save_9/RestoreV2/tensor_names, save_9/RestoreV2/shape_and_slices)]]",
      "\nDuring handling of the above exception, another exception occurred:\n",
      "\u001b[1;31mNotFoundError\u001b[0m                             Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-52-1c6db3348267>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[0;32m     94\u001b[0m \u001b[1;32mwith\u001b[0m \u001b[0mtf\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mSession\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0msess\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     95\u001b[0m     \u001b[1;31m#sess.run(init) #不使用训练好的参数\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 96\u001b[1;33m     \u001b[0mload_path\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0msaver\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrestore\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0msess\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;34m\"./result/Test_MNIST_model.ckpt\"\u001b[0m\u001b[1;33m)\u001b[0m  \u001b[1;31m#load上一步训练的参数\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     97\u001b[0m     \u001b[0mstep\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     98\u001b[0m     \u001b[1;31m# Keep training until reach max iterations\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mE:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\training\\saver.py\u001b[0m in \u001b[0;36mrestore\u001b[1;34m(self, sess, save_path)\u001b[0m\n\u001b[0;32m   1800\u001b[0m     \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1801\u001b[0m       sess.run(self.saver_def.restore_op_name,\n\u001b[1;32m-> 1802\u001b[1;33m                {self.saver_def.filename_tensor_name: save_path})\n\u001b[0m\u001b[0;32m   1803\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1804\u001b[0m   \u001b[1;33m@\u001b[0m\u001b[0mstaticmethod\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mE:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\client\\session.py\u001b[0m in \u001b[0;36mrun\u001b[1;34m(self, fetches, feed_dict, options, run_metadata)\u001b[0m\n\u001b[0;32m    898\u001b[0m     \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    899\u001b[0m       result = self._run(None, fetches, feed_dict, options_ptr,\n\u001b[1;32m--> 900\u001b[1;33m                          run_metadata_ptr)\n\u001b[0m\u001b[0;32m    901\u001b[0m       \u001b[1;32mif\u001b[0m \u001b[0mrun_metadata\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    902\u001b[0m         \u001b[0mproto_data\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mtf_session\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mTF_GetBuffer\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mrun_metadata_ptr\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mE:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\client\\session.py\u001b[0m in \u001b[0;36m_run\u001b[1;34m(self, handle, fetches, feed_dict, options, run_metadata)\u001b[0m\n\u001b[0;32m   1133\u001b[0m     \u001b[1;32mif\u001b[0m \u001b[0mfinal_fetches\u001b[0m \u001b[1;32mor\u001b[0m \u001b[0mfinal_targets\u001b[0m \u001b[1;32mor\u001b[0m \u001b[1;33m(\u001b[0m\u001b[0mhandle\u001b[0m \u001b[1;32mand\u001b[0m \u001b[0mfeed_dict_tensor\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1134\u001b[0m       results = self._do_run(handle, final_targets, final_fetches,\n\u001b[1;32m-> 1135\u001b[1;33m                              feed_dict_tensor, options, run_metadata)\n\u001b[0m\u001b[0;32m   1136\u001b[0m     \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1137\u001b[0m       \u001b[0mresults\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;33m[\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mE:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\client\\session.py\u001b[0m in \u001b[0;36m_do_run\u001b[1;34m(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)\u001b[0m\n\u001b[0;32m   1314\u001b[0m     \u001b[1;32mif\u001b[0m \u001b[0mhandle\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1315\u001b[0m       return self._do_call(_run_fn, feeds, fetches, targets, options,\n\u001b[1;32m-> 1316\u001b[1;33m                            run_metadata)\n\u001b[0m\u001b[0;32m   1317\u001b[0m     \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1318\u001b[0m       \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_do_call\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0m_prun_fn\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mhandle\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfeeds\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfetches\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mE:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\client\\session.py\u001b[0m in \u001b[0;36m_do_call\u001b[1;34m(self, fn, *args)\u001b[0m\n\u001b[0;32m   1333\u001b[0m         \u001b[1;32mexcept\u001b[0m \u001b[0mKeyError\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1334\u001b[0m           \u001b[1;32mpass\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1335\u001b[1;33m       \u001b[1;32mraise\u001b[0m \u001b[0mtype\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0me\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mnode_def\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mop\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mmessage\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1336\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1337\u001b[0m   \u001b[1;32mdef\u001b[0m \u001b[0m_extend_graph\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mNotFoundError\u001b[0m: Key Variable_100 not found in checkpoint\n\t [[Node: save_9/RestoreV2 = RestoreV2[dtypes=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, ..., DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT], _device=\"/job:localhost/replica:0/task:0/device:CPU:0\"](_arg_save_9/Const_0_0, save_9/RestoreV2/tensor_names, save_9/RestoreV2/shape_and_slices)]]\n\nCaused by op 'save_9/RestoreV2', defined at:\n  File \"E:\\ProgramData\\Anaconda3\\lib\\runpy.py\", line 193, in _run_module_as_main\n    \"__main__\", mod_spec)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\runpy.py\", line 85, in _run_code\n    exec(code, run_globals)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\ipykernel_launcher.py\", line 16, in <module>\n    app.launch_new_instance()\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\traitlets\\config\\application.py\", line 658, in launch_instance\n    app.start()\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\ipykernel\\kernelapp.py\", line 486, in start\n    self.io_loop.start()\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\tornado\\platform\\asyncio.py\", line 127, in start\n    self.asyncio_loop.run_forever()\n  File \"E:\\ProgramData\\Anaconda3\\lib\\asyncio\\base_events.py\", line 422, in run_forever\n    self._run_once()\n  File \"E:\\ProgramData\\Anaconda3\\lib\\asyncio\\base_events.py\", line 1432, in _run_once\n    handle._run()\n  File \"E:\\ProgramData\\Anaconda3\\lib\\asyncio\\events.py\", line 145, in _run\n    self._callback(*self._args)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\tornado\\ioloop.py\", line 759, in _run_callback\n    ret = callback()\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\tornado\\stack_context.py\", line 276, in null_wrapper\n    return fn(*args, **kwargs)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\zmq\\eventloop\\zmqstream.py\", line 536, in <lambda>\n    self.io_loop.add_callback(lambda : self._handle_events(self.socket, 0))\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\zmq\\eventloop\\zmqstream.py\", line 450, in _handle_events\n    self._handle_recv()\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\zmq\\eventloop\\zmqstream.py\", line 480, in _handle_recv\n    self._run_callback(callback, msg)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\zmq\\eventloop\\zmqstream.py\", line 432, in _run_callback\n    callback(*args, **kwargs)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\tornado\\stack_context.py\", line 276, in null_wrapper\n    return fn(*args, **kwargs)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\ipykernel\\kernelbase.py\", line 283, in dispatcher\n    return self.dispatch_shell(stream, msg)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\ipykernel\\kernelbase.py\", line 233, in dispatch_shell\n    handler(stream, idents, msg)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\ipykernel\\kernelbase.py\", line 399, in execute_request\n    user_expressions, allow_stdin)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\ipykernel\\ipkernel.py\", line 208, in do_execute\n    res = shell.run_cell(code, store_history=store_history, silent=silent)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\ipykernel\\zmqshell.py\", line 537, in run_cell\n    return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\IPython\\core\\interactiveshell.py\", line 2662, in run_cell\n    raw_cell, store_history, silent, shell_futures)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\IPython\\core\\interactiveshell.py\", line 2785, in _run_cell\n    interactivity=interactivity, compiler=compiler, result=result)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\IPython\\core\\interactiveshell.py\", line 2903, in run_ast_nodes\n    if self.run_code(code, result):\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\IPython\\core\\interactiveshell.py\", line 2963, in run_code\n    exec(code_obj, self.user_global_ns, self.user_ns)\n  File \"<ipython-input-52-1c6db3348267>\", line 92, in <module>\n    saver = tf.train.Saver()  ##保存的API\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\training\\saver.py\", line 1338, in __init__\n    self.build()\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\training\\saver.py\", line 1347, in build\n    self._build(self._filename, build_save=True, build_restore=True)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\training\\saver.py\", line 1384, in _build\n    build_save=build_save, build_restore=build_restore)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\training\\saver.py\", line 835, in _build_internal\n    restore_sequentially, reshape)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\training\\saver.py\", line 472, in _AddRestoreOps\n    restore_sequentially)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\training\\saver.py\", line 886, in bulk_restore\n    return io_ops.restore_v2(filename_tensor, names, slices, dtypes)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\ops\\gen_io_ops.py\", line 1546, in restore_v2\n    shape_and_slices=shape_and_slices, dtypes=dtypes, name=name)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\framework\\op_def_library.py\", line 787, in _apply_op_helper\n    op_def=op_def)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\framework\\ops.py\", line 3392, in create_op\n    op_def=op_def)\n  File \"E:\\ProgramData\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\framework\\ops.py\", line 1718, in __init__\n    self._traceback = self._graph._extract_stack()  # pylint: disable=protected-access\n\nNotFoundError (see above for traceback): Key Variable_100 not found in checkpoint\n\t [[Node: save_9/RestoreV2 = RestoreV2[dtypes=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, ..., DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT], _device=\"/job:localhost/replica:0/task:0/device:CPU:0\"](_arg_save_9/Const_0_0, save_9/RestoreV2/tensor_names, save_9/RestoreV2/shape_and_slices)]]\n"
     ]
    }
   ],
   "source": [
    "from __future__ import print_function\n",
    "import tensorflow as tf\n",
    "# Import MNIST data\n",
    "from tensorflow.examples.tutorials.mnist import input_data\n",
    "mnist = input_data.read_data_sets(\"./MNIST_data\", one_hot=True)\n",
    "\n",
    "# Parameters\n",
    "learning_rate = 0.001\n",
    "training_iters = 128*10*300 \n",
    "batch_size = 128\n",
    "display_step = 10\n",
    "\n",
    "# Network Parameters\n",
    "n_input = 784 # MNIST data input (img shape: 28*28)\n",
    "n_classes = 10 # MNIST total classes (0-9 digits)\n",
    "dropout = 0.75 # Dropout, probability to keep units\n",
    "\n",
    "# tf Graph input\n",
    "x = tf.placeholder(tf.float32, [None, n_input])\n",
    "y = tf.placeholder(tf.float32, [None, n_classes])\n",
    "keep_prob = tf.placeholder(tf.float32) #dropout (keep probability)\n",
    "\n",
    "# Create some wrappers for simplicity\n",
    "def conv2d(x, W, b, strides=1):\n",
    "    # Conv2D wrapper, with bias and relu activation\n",
    "    x = tf.nn.conv2d(x, W, strides=[1, strides, strides, 1], padding='SAME')\n",
    "    x = tf.nn.bias_add(x, b)\n",
    "    return tf.nn.relu(x)\n",
    "\n",
    "def maxpool2d(x, k=2):\n",
    "    # MaxPool2D wrapper\n",
    "    return tf.nn.max_pool(x, ksize=[1, k, k, 1], strides=[1, k, k, 1],\n",
    "                          padding='SAME')\n",
    "\n",
    "# Create model\n",
    "def conv_net(x, weights, biases, dropout):\n",
    "    # Reshape input picture\n",
    "    x = tf.reshape(x, shape=[-1, 28, 28, 1])\n",
    "\n",
    "    # Convolution Layer\n",
    "    conv1 = conv2d(x, weights['wc1'], biases['bc1'])\n",
    "    # Max Pooling (down-sampling)\n",
    "    conv1 = maxpool2d(conv1, k=2)\n",
    "\n",
    "    # Convolution Layer\n",
    "    conv2 = conv2d(conv1, weights['wc2'], biases['bc2'])\n",
    "    # Max Pooling (down-sampling)\n",
    "    conv2 = maxpool2d(conv2, k=2)\n",
    "\n",
    "    # Fully connected layer\n",
    "    # Reshape conv2 output to fit fully connected layer input\n",
    "    fc1 = tf.reshape(conv2, [-1, weights['wd1'].get_shape().as_list()[0]])\n",
    "    fc1 = tf.add(tf.matmul(fc1, weights['wd1']), biases['bd1'])\n",
    "    fc1 = tf.nn.relu(fc1)\n",
    "    # Apply Dropout\n",
    "    fc1 = tf.nn.dropout(fc1, dropout)\n",
    "\n",
    "    # Output, class prediction\n",
    "    out = tf.add(tf.matmul(fc1, weights['out']), biases['out'])\n",
    "    return out\n",
    "\n",
    "# Store layers weight & bias\n",
    "weights = {\n",
    "    # 5x5 conv, 1 input, 32 outputs\n",
    "    'wc1': tf.Variable(tf.random_normal([5, 5, 1, 32])),\n",
    "    # 5x5 conv, 32 inputs, 64 outputs\n",
    "    'wc2': tf.Variable(tf.random_normal([5, 5, 32, 64])),\n",
    "    # fully connected, 7*7*64 inputs, 1024 outputs\n",
    "    'wd1': tf.Variable(tf.random_normal([7*7*64, 1024])),\n",
    "    # 1024 inputs, 10 outputs (class prediction)\n",
    "    'out': tf.Variable(tf.random_normal([1024, n_classes]))\n",
    "}\n",
    "\n",
    "biases = {\n",
    "    'bc1': tf.Variable(tf.random_normal([32])),\n",
    "    'bc2': tf.Variable(tf.random_normal([64])),\n",
    "    'bd1': tf.Variable(tf.random_normal([1024])),\n",
    "    'out': tf.Variable(tf.random_normal([n_classes]))\n",
    "}\n",
    "\n",
    "# Construct model\n",
    "pred = conv_net(x, weights, biases, keep_prob)\n",
    "#注意这里的变化，上面pred得到的是10个类每个类的概率值，概率值最高说明这个类就是预测的类，坐标对应0-9，所以利用下面这行代码，将预测值输出出来，tf.argmax方法是将每行向量中值最高的下标返回过来，这个下标对应的也就是类别。\n",
    "pred_class_index=tf.argmax(pred, 1)\n",
    "# # Evaluate model\n",
    "correct_pred = tf.equal(pred_class_index, tf.argmax(y, 1))\n",
    "accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))\n",
    "\n",
    "# Initializing the variables\n",
    "init = tf.global_variables_initializer()\n",
    "\n",
    "saver = tf.train.Saver()  ##保存的API\n",
    "# Launch the graph\n",
    "with tf.Session() as sess:\n",
    "    #sess.run(init) #不使用训练好的参数\n",
    "    load_path = saver.restore(sess,\"./result/Test_MNIST_model.ckpt\")  #load上一步训练的参数\n",
    "    step = 1\n",
    "    # Keep training until reach max iterations\n",
    "    batch_x=mnist.test.images[:256]\n",
    "    batch_y=mnist.test.labels[:256]\n",
    "    print (\"batch_y:\",batch_y)\n",
    "    # Calculate batch loss and accuracy\n",
    "    pred_value = sess.run([pred_class_index], feed_dict={x: batch_x, y: batch_y,keep_prob: 1.})\n",
    "    print(\"pred_value:\",pred_value)\n",
    "    # Calculate accuracy for 256 mnist test images\n",
    "    # mnist部分测试数据集，用刚刚训练好的模型来做预测。\n",
    "    print(\"Testing Accuracy:\", \\\n",
    "        sess.run(accuracy, feed_dict={x: mnist.test.images[:256],\n",
    "                                      y: mnist.test.labels[:256],\n",
    "                                      keep_prob: 1.}))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}